{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T21:11:42Z","timestamp":1774473102271,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","funder":[{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LQN25F030014, LDT23F02025F02"],"award-info":[{"award-number":["LQN25F030014, LDT23F02025F02"]}]},{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62422204, 62072147"],"award-info":[{"award-number":["62422204, 62072147"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1145\/3731715.3733393","type":"proceedings-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T18:31:04Z","timestamp":1750876264000},"page":"1767-1776","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["MMCNav: MLLM-empowered Multi-agent Collaboration for Outdoor Visual Language Navigation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3480-0212","authenticated-orcid":false,"given":"Ziheng","family":"Zhang","sequence":"first","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0418-7665","authenticated-orcid":false,"given":"Minghao","family":"Chen","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8243-1127","authenticated-orcid":false,"given":"Suguo","family":"Zhu","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2131-9200","authenticated-orcid":false,"given":"Tingting","family":"Han","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8407-1137","authenticated-orcid":false,"given":"Zhou","family":"Yu","sequence":"additional","affiliation":[{"name":"Hangzhou Dianzi University, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,6,30]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"An integrated theory of the mind. Psychological review","author":"Anderson John R","year":"2004","unstructured":"John R Anderson, Daniel Bothell, Michael D Byrne, Scott Douglass, Christian Lebiere, and Yulin Qin. 2004. An integrated theory of the mind. Psychological review, Vol. 111, 4 (2004), 1036."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"e_1_3_2_1_4_1","volume-title":"3rd Annual Conference on Robot Learning, CoRL 2019, Osaka, Japan, October 30 - November 1, 2019, Proceedings (Proceedings of Machine Learning Research","volume":"1438","author":"Blukis Valts","year":"2019","unstructured":"Valts Blukis, Yannick Terme, Eyvind Niklasson, Ross A. Knepper, and Yoav Artzi. 2019. Learning to Map Natural Language Instructions to Physical Quadcopter Control using Simulated Flight. In 3rd Annual Conference on Robot Learning, CoRL 2019, Osaka, Japan, October 30 - November 1, 2019, Proceedings (Proceedings of Machine Learning Research, Vol. 100), Leslie Pack Kaelbling, Danica Kragic, and Komei Sugiura (Eds.). PMLR, 1415--1438."},{"key":"e_1_3_2_1_5_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11832"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v25i1.7974"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01282"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.529"},{"key":"e_1_3_2_1_11_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2831228"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.190"},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings, Part VI 16","author":"Fu Tsu-Jui","year":"2020","unstructured":"Tsu-Jui Fu, Xin Eric Wang, Matthew F Peterson, Scott T Grafton, Miguel P Eckstein, and William Yang Wang. 2020. Counterfactual vision-and-language navigation via adversarial path sampler. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part VI 16. Springer, 71--86."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/890"},{"key":"e_1_3_2_1_16_1","volume-title":"LLM multi-agent systems: Challenges and open problems. arXiv preprint arXiv:2402.03578","author":"Han Shanshan","year":"2024","unstructured":"Shanshan Han, Qifan Zhang, Yuhang Yao, Weizhao Jin, Zhaozhuo Xu, and Chaoyang He. 2024. LLM multi-agent systems: Challenges and open problems. arXiv preprint arXiv:2402.03578 (2024)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6849"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Enkelejda Kasneci Kathrin Se\u00dfler Stefan K\u00fcchemann Maria Bannert Daryna Dementieva Frank Fischer Urs Gasser Georg Groh Stephan G\u00fcnnemann Eyke H\u00fcllermeier et al. 2023. ChatGPT for good? On opportunities and challenges of large language models for education. Learning and individual differences Vol. 103 (2023) 102274.","DOI":"10.1016\/j.lindif.2023.102274"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3141150"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3407759"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611565"},{"key":"e_1_3_2_1_24_1","first-page":"2507","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume":"35","author":"Lu Pan","year":"2022","unstructured":"Pan Lu, Swaroop Mishra, Tanglin Xia, Liang Qiu, Kai-Wei Chang, Song-Chun Zhu, Oyvind Tafjord, Peter Clark, and Ashwin Kalyan. 2022. Learn to explain: Multimodal reasoning via thought chains for science question answering. Advances in Neural Information Processing Systems, Vol. 35 (2022), 2507--2521.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_25_1","first-page":"4","article-title":"Walk the talk: Connecting language, knowledge, and action in route instructions","volume":"2","author":"MacMahon Matt","year":"2006","unstructured":"Matt MacMahon, Brian Stankiewicz, and Benjamin Kuipers. 2006. Walk the talk: Connecting language, knowledge, and action in route instructions. Def, Vol. 2, 6 (2006), 4.","journal-title":"Def"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings, Part VI 16","author":"Majumdar Arjun","year":"2020","unstructured":"Arjun Majumdar, Ayush Shrivastava, Stefan Lee, Peter Anderson, Devi Parikh, and Dhruv Batra. 2020. Improving vision-and-language navigation with image-text pairs from the web. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part VI 16. Springer, 259--274."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610855"},{"key":"e_1_3_2_1_28_1","volume-title":"Mateusz Malinowski, Matthew Koichi Grimes, Karen Simonyan, Koray Kavukcuoglu, Andrew Zisserman, et al.","author":"Mirowski Piotr","year":"2019","unstructured":"Piotr Mirowski, Andras Banki-Horvath, Keith Anderson, Denis Teplyashin, Karl Moritz Hermann, Mateusz Malinowski, Matthew Koichi Grimes, Karen Simonyan, Koray Kavukcuoglu, Andrew Zisserman, et al. 2019. The streetlearn environment and dataset. arXiv preprint arXiv:1903.01292 (2019)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/3327144.3327168"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01281"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19--1681"},{"key":"e_1_3_2_1_32_1","volume-title":"RUN through the streets: A new dataset and baseline models for realistic urban navigation. arXiv preprint arXiv:1909.08970","author":"Paz-Argaman Tzuf","year":"2019","unstructured":"Tzuf Paz-Argaman and Reut Tsarfaty. 2019b. RUN through the streets: A new dataset and baseline models for realistic urban navigation. arXiv preprint arXiv:1909.08970 (2019)."},{"key":"e_1_3_2_1_33_1","volume-title":"HOP: History-enhanced and Order-aware Pre-training for Vision-and-Language Navigation","author":"Qiao Yanyuan","year":"2023","unstructured":"Yanyuan Qiao, Yuankai Qi, Yicong Hong, Zheng Yu, Peng Wang, and Qi Wu. 2023. HOP: History-enhanced and Order-aware Pre-training for Vision-and-Language Navigation. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)."},{"key":"e_1_3_2_1_34_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.41"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.518"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29858"},{"key":"e_1_3_2_1_38_1","volume-title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https:\/\/arxiv.org\/abs\/1912","author":"Shridhar Mohit","year":"2020","unstructured":"Mohit Shridhar, Jesse Thomason, Daniel Gordon, Yonatan Bisk, Winson Han, Roozbeh Mottaghi, Luke Zettlemoyer, and Dieter Fox. 2020. ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https:\/\/arxiv.org\/abs\/1912.01734"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01365"},{"key":"e_1_3_2_1_40_1","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew M Dai Anja Hauth Katie Millican et al. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681518"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_1_43_1","volume-title":"Voyager: An open-ended embodied agent with large language models. arXiv preprint arXiv:2305.16291","author":"Wang Guanzhi","year":"2023","unstructured":"Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, and Anima Anandkumar. 2023. Voyager: An open-ended embodied agent with large language models. arXiv preprint arXiv:2305.16291 (2023)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40231-1"},{"key":"e_1_3_2_1_45_1","volume-title":"Xin Eric Wang, and William Yang Wang","author":"Xiang Jiannan","year":"2020","unstructured":"Jiannan Xiang, Xin Eric Wang, and William Yang Wang. 2020. Learning to stop: A simple yet effective approach to urban vision-language navigation. arXiv preprint arXiv:2009.13112 (2020)."},{"key":"e_1_3_2_1_46_1","volume-title":"Exploring large language models for communication games: An empirical study on werewolf. arXiv preprint arXiv:2309.04658","author":"Xu Yuzhuang","year":"2023","unstructured":"Yuzhuang Xu, Shuo Wang, Peng Li, Fuwen Luo, Xiaolong Wang, Weidong Liu, and Yang Liu. 2023. Exploring large language models for communication games: An empirical study on werewolf. arXiv preprint arXiv:2309.04658 (2023)."},{"key":"e_1_3_2_1_47_1","volume-title":"A survey on multimodal large language models. arXiv preprint arXiv:2306.13549","author":"Yin Shukang","year":"2023","unstructured":"Shukang Yin, Chaoyou Fu, Sirui Zhao, Ke Li, Xing Sun, Tong Xu, and Enhong Chen. 2023. A survey on multimodal large language models. arXiv preprint arXiv:2306.13549 (2023)."},{"key":"e_1_3_2_1_48_1","volume-title":"Building cooperative embodied agents modularly with large language models. arXiv preprint arXiv:2307.02485","author":"Zhang Hongxin","year":"2023","unstructured":"Hongxin Zhang, Weihua Du, Jiaming Shan, Qinhong Zhou, Yilun Du, Joshua B Tenenbaum, Tianmin Shu, and Chuang Gan. 2023. Building cooperative embodied agents modularly with large language models. arXiv preprint arXiv:2307.02485 (2023)."},{"key":"e_1_3_2_1_49_1","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics. 5745--5754","author":"Zhang Yue","year":"2022","unstructured":"Yue Zhang and Parisa Kordjamshidi. 2022. LOViS: Learning Orientation and Visual Signals for Vision and Language Navigation. In Proceedings of the 29th International Conference on Computational Linguistics. 5745--5754."},{"key":"e_1_3_2_1_50_1","volume-title":"Diagnosing the environment bias in vision-and-language navigation. arXiv preprint arXiv:2005.03086","author":"Zhang Yubo","year":"2020","unstructured":"Yubo Zhang, Hao Tan, and Mohit Bansal. 2020. Diagnosing the environment bias in vision-and-language navigation. arXiv preprint arXiv:2005.03086 (2020)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.103"}],"event":{"name":"ICMR '25: International Conference on Multimedia Retrieval","location":"Chicago IL USA","acronym":"ICMR '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2025 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731715.3733393","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T04:06:30Z","timestamp":1755749190000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731715.3733393"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":51,"alternative-id":["10.1145\/3731715.3733393","10.1145\/3731715"],"URL":"https:\/\/doi.org\/10.1145\/3731715.3733393","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]},"assertion":[{"value":"2025-06-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}